LS GM Professional Image Engine
Paste the following prompt into your AI chat to install this skill:
Please install @lishengvision/ls-gm-img following https://skillhub.cn/install/skillhub.md.
About this skill
Problem
Batch image work often trips on output sizes, formats, white borders, shadows, GIF weight, and cross-shell command differences. Reusing raw gm convert, gm montage, or append parameters manually can repeat the same mistakes: misaligned appends, missing format delegates, font errors, or resource limits.
How it works
@lishengvision/ls-gm-img wraps GraphicsMagick into practical workflows. It exposes presets for WeChat article images, e-commerce main images, avatars, landscape posters, and ID photos, then maps them to gm convert, gm mogrify, gm identify, gm composite, gm montage, gm animate, and gm compare. The skill covers format conversion, resize and crop, rotation and flipping, color and quality adjustment, sharpening and blur, text and watermark effects, image appending, montage grids, pixel-level comparison, and animated GIFs.
Boundaries
It assumes a working gm environment. Some builds may lack format decoders or default fonts. Command syntax also varies by shell, so wildcards, quotes, path separators, and bracket escaping need care. Append operations should align edge dimensions first, and large files should be constrained with -limit.
Use Cases
- Editors preparing WeChat articles need to convert multiple images to 800px-wide WebP with shadows.
- Operators listing products need to crop product shots into 800x800 white main images and 750px detail images.
- Content teams making campaign assets need to append screenshots into landscape posters with text and watermarks.
- Front-end engineers preparing motion assets need to create GIFs, tune frame delays, and reduce file size.
Best For
- Editors preparing WeChat article images need batch outputs at fixed width, WebP, and shadows.
- E-commerce operators listing products need white-background square main images, detail images, and avatars.
- Front-end engineers building motion assets need multi-frame GIFs, per-frame delays, and smaller files.
- Test or docs engineers processing screenshots need appending, image comparison, metadata, and format normalization.
Related Skills
Convert Chinese or natural-language requests into paste-ready English image prompts for ChatGPT's web UI, covering generation, editing, multi-image references, and exact text without performing image generation.
A creative AI image workflow for style transfer, reference-based creation, scene replacement, series expansion, material conversion, era shifts, composition rework, lineart conversion, and cartoonization.
Translates star-inspired football memories and fan resonance into compliant original IP poster concepts while avoiding real names, likenesses, official badges, and event logos.
Extracts real web page colors, typography, components, layouts, and interaction styles with a Playwright script to produce a verifiable design guideline.